110 Deep Research Pro

Multi-source deep research agent. Searches the web, synthesizes findings, and delivers cited reports. No API keys required.

Security Scan

The skill's stated research purpose is plausible, but multiple inconsistencies and hard-coded external-script dependencies (paths to another skill's ddg script), missing files referenced in metadata, and absolute paths in runtime instructions make its behavior unclear and worth closer review before installing.

Purpose & Capability

The skill claims to perform web research without API keys, which fits the description. However it requires a specific external script at /home/clawdbot/clawd/skills/ddg-search/scripts/ddg (not included) and references a local scripts/research CLI that is not present in the file manifest. Requiring another skill's executable via a hard-coded path is disproportionate and fragile — a legitimate research skill would include or document that dependency clearly.

Instruction Scope

SKILL.md instructs the agent to run absolute-path binaries and to fetch arbitrary URLs via curl and a python one-liner (which strips HTML with regex). It also tells sub-agents to read specific local paths (/home/clawdbot/...) and to save reports under ~/clawd/research. While fetching pages and saving reports is expected for research, the use of absolute paths to other skills, spawning sub-agents with explicit file reads, and executing fetched content-processing one-liners widen the operational scope and could lead to surprising behavior if those paths or scripts do not match the host environment.

Install Mechanism

There is no install spec (instruction-only), which minimizes on-disk installation risk. However the README/package.json advertise scripts and auto-installing dependencies (uv, scripts/research) that are not present in the package manifest, indicating packaging inconsistencies that should be resolved.

Credentials

The skill declares no required environment variables, no credentials, and no config paths. That is proportionate to a web-research skill that uses public search and curl; there are no requests for unrelated secrets.

Persistence & Privilege

always:false and no attempt to modify other skills or system-wide configs. The skill saves reports into the user's home directory (~/clawd/research) which is reasonable for its purpose. Spawning sub-agents is allowed by default and not, by itself, a red flag.

What to consider before installing

Do not install blindly. Before using the skill, verify these points: 1) Check that the referenced ddg-search script actually exists at /home/clawdbot/clawd/skills/ddg-search/scripts/ddg (or update SKILL.md to a relative or documented dependency). 2) Confirm the repository and author — README git URL (https://github.com/parags/deep-research-pro) and homepage/owner metadata are inconsistent with registry metadata; this could be a packaging error. 3) The package advertises scripts/research and auto-install behavior, but those files are missing from the manifest — ask the author for a complete package or include the missing scripts. 4) Review the curl + python one-liner logic (it strips HTML via regex) and consider running fetches in a sandbox — fetching arbitrary URLs and processing their contents can have security and privacy implications. 5) If you will allow the agent to spawn sub-agents, ensure your agent's policy and the 'sessions_spawn' mechanism are safe in your environment (model name and read-paths are hard-coded). If you cannot confirm these items, run the skill in an isolated environment or request a corrected, complete release from the maintainer.

Deep Research Pro 🔬

A powerful, self-contained deep research skill that produces thorough, cited reports from multiple web sources. No paid APIs required — uses DuckDuckGo search.

How It Works

When the user asks for research on any topic, follow this workflow:

Step 1: Understand the Goal (30 seconds)

Ask 1-2 quick clarifying questions:

• "What's your goal — learning, making a decision, or writing something?"
• "Any specific angle or depth you want?"

If the user says "just research it" — skip ahead with reasonable defaults.

Step 2: Plan the Research (think before searching)

Break the topic into 3-5 research sub-questions. For example:

• Topic: "Impact of AI on healthcare"
  • What are the main AI applications in healthcare today?
  • What clinical outcomes have been measured?
  • What are the regulatory challenges?
  • What companies are leading this space?
  • What's the market size and growth trajectory?

Step 3: Execute Multi-Source Search

For EACH sub-question, run the DDG search script:

# Web search
/home/clawdbot/clawd/skills/ddg-search/scripts/ddg "<sub-question keywords>" --max 8

# News search (for current events)
/home/clawdbot/clawd/skills/ddg-search/scripts/ddg news "<topic>" --max 5

Search strategy:

• Use 2-3 different keyword variations per sub-question
• Mix web + news searches
• Aim for 15-30 unique sources total
• Prioritize: academic, official, reputable news > blogs > forums

Step 4: Deep-Read Key Sources

For the most promising URLs, fetch full content:

curl -sL "<url>" | python3 -c "
import sys, re
html = sys.stdin.read()
# Strip tags, get text
text = re.sub('<[^>]+>', ' ', html)
text = re.sub(r'\s+', ' ', text).strip()
print(text[:5000])
"

Read 3-5 key sources in full for depth. Don't just rely on search snippets.

Step 5: Synthesize & Write Report

Structure the report as:

# [Topic]: Deep Research Report
*Generated: [date] | Sources: [N] | Confidence: [High/Medium/Low]*

## Executive Summary
[3-5 sentence overview of key findings]

## 1. [First Major Theme]
[Findings with inline citations]
- Key point ([Source Name](url))
- Supporting data ([Source Name](url))

## 2. [Second Major Theme]
...

## 3. [Third Major Theme]
...

## Key Takeaways
- [Actionable insight 1]
- [Actionable insight 2]
- [Actionable insight 3]

## Sources
1. [Title](url) — [one-line summary]
2. ...

## Methodology
Searched [N] queries across web and news. Analyzed [M] sources.
Sub-questions investigated: [list]

Step 6: Save & Deliver

Save the full report:

mkdir -p ~/clawd/research/[slug]
# Write report to ~/clawd/research/[slug]/report.md

Then deliver:

• Short topics: Post the full report in chat
• Long reports: Post the executive summary + key takeaways, offer full report as file

Quality Rules

1. Every claim needs a source. No unsourced assertions.
2. Cross-reference. If only one source says it, flag it as unverified.
3. Recency matters. Prefer sources from the last 12 months.
4. Acknowledge gaps. If you couldn't find good info on a sub-question, say so.
5. No hallucination. If you don't know, say "insufficient data found."

Examples

"Research the current state of nuclear fusion energy"
"Deep dive into Rust vs Go for backend services in 2026"
"Research the best strategies for bootstrapping a SaaS business"
"What's happening with the US housing market right now?"

For Sub-Agent Usage

When spawning as a sub-agent, include the full research request and context:

sessions_spawn(
  task: "Run deep research on [TOPIC]. Follow the deep-research-pro SKILL.md workflow.
  Read /home/clawdbot/clawd/skills/deep-research-pro/SKILL.md first.
  Goal: [user's goal]
  Specific angles: [any specifics]
  Save report to ~/clawd/research/[slug]/report.md
  When done, wake the main session with key findings.",
  label: "research-[slug]",
  model: "opus"
)

Requirements

• DDG search script: /home/clawdbot/clawd/skills/ddg-search/scripts/ddg
• curl (for fetching full pages)
• No API keys needed!